© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1457
    Prev
    Next
    INDEX
    Explanations

    question-related phrases and inquiries about understanding or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Questions and introductions

    np_acts-logits-general · gemini-2.0-flash

    usefulness and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TemporalType
    -0.50
     ब्रेकडाउन
    -0.47
    guém
    -0.47
     zoude
    -0.46
    findpost
    -0.45
     geïsole
    -0.44
     Meksiku
    -0.43
    épend
    -0.43
    __":
    -0.43
    zuführen
    -0.43
    POSITIVE LOGITS
    AccessorTable
    0.59
    IntoConstraints
    0.52
    setVerticalGroup
    0.40
     goals
    0.39
     benefits
    0.39
     صوتيه
    0.37
     implication
    0.35
     aims
    0.35
     ویکی‌آمباردا
    0.35
    دانشنامهٔ
    0.35
    Activations Density 0.329%

    No Known Activations